Flexible Visual Summaries of High-Dimensional Data using Hierarchical Aggregated Data-Subsets

David Pfahler

Supervisor(s): Harald Piringer

VRVis Research Center


Abstract: The number of installed sensors to acquire data, for example electricity meters in smart grids, is increasing rapidly. This huge amount of collected data needs to be analyzed and monitored by transmission system operators. This task is supported by visual analytics techniques, but traditional multi-dimensional data visualization techniques do not scale very well for high-dimensional data. The main contribution of this paper is a framework to efficiently inspect and compare such high-dimensional data. The key idea is to partition the data by the semantics of the underlying data dimensions into groups. Domain experts are familiar with the meta-information of the data and are able to structure these groups into a hierarchy. The proposed system visualizes the subsets of the data by appropriate means. These visual summaries can then be used to support the explorative overview tasks of the user.
Keywords: Scientific Visualization
Full text:
Year: 2017